Yuehao Wang

Yuehao Wang

Ph.D. Student
Department of Computer Science
The University of Texas at Austin

yuehao [at] utexas.edu
[Scholar] [Github] [LinkedIn] [Twitter]

I am a Ph.D. student at UT Austin with VITA Group, advised by Prof. Atlas Wang and Prof. Qixing Huang. Before that, I did my Master of Philosophy at CUHK, where I was fortunate to work with Prof. Tianfan Xue. I obtained my bachelor's degree from ShanghaiTech University.

Research

My current research interests include computer graphics, computer vision, machine learning, and computational photography. In particular, I work on projects in generative models, neural rendering, and 3D scene reconstruction. Below are my research publications.

Note: * indicates authors with equal contribution.

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing

Peihao Wang, Ruisi Cai, Yuehao Wang, Jiajun Zhu, Pragya Srivastava, Zhangyang Wang, Pan Li

ICLR, 2025

We show that SSMs suffer from recency bias and over-smoothing, and propose a polarization technique to improve long-range recall and enable deeper SSMs.

[Paper] [Code]

Bilateral Guided Radiance Field Processing

Yuehao Wang, Chaoyi Wang, Bingchen Gong, Tianfan Xue

SIGGRAPH (ACM TOG), 2024 (Best Paper Honorable Mention)

We introduce 2D and 3D image signal processing (ISP) pipelines to radiance fields for handling photometric variation and retouching 3D scenes.

[Paper] [Code] [Webpage]

SeamlessNeRF: Stitching Part NeRFs with Gradient Propagation

Bingchen Gong*, Yuehao Wang*, Xiaoguang Han, Qi Dou

SIGGRAPH Asia, 2023

We present a gradient domain approach for seamless appearance blending of part NeRFs, drawing inspiration from Poisson image editing.

[Paper] [Webpage]

RecolorNeRF: Layer Decomposed Radiance Fields for Efficient Color Editing of 3D Scenes

Bingchen Gong*, Yuehao Wang*, Xiaoguang Han, Qi Dou

ACM MM, 2023

We decompose NeRF into pure-color layers for palette-based color editing of 3D scenes.

[Paper] [Code] [Webpage]

Neural Rendering for Stereo 3D Reconstruction of Deformable Tissues in Robotic Surgery

Yuehao Wang, Yonghao Long, Siu Hin Fan, Qi Dou

MICCAI, 2022 (Oral Presentation, Student Travel Award, Young Scientist Award)

A NeRF-based method for reconstructing deformable tissues from stereo endoscopic images.

[Paper] [Code] [Webpage]

Multi-view Neural Human Rendering

Minye Wu, Yuehao Wang, Qiang Hu, Jingyi Yu

CVPR, 2020

We present an end-to-end Neural Human Renderer (NHR) for dynamic human captures under the multi-view setting.

[Paper] [Code] [Webpage]

Coding Projects

Interactive Volume Renderer

An interactive volume visualizer for displaying implicit functions, medical data, smoke, etc., using CUDA for real-time rendering.

View on Github Videos

Let's Compute Graphics

A course project collection of graphics algorithms and applications, including OpenGL, global illumination, Loop subdivision, etc.

View on Github

Talks & Presentations

Invited talk at Xiamen University: "Radiance Field Processing", Sep 2024.
Conference presentation at SIGGRAPH 2024: "Bilateral Guided Radiance Field Processing", Aug 2024.
Invited talk at OpenRobotLab @ Shanghai AI Laboratory: "Editable Representations for NeRF", Jan 2024.
Invited talk at Olympus ATR: "3D Reconstruction of Deformable Soft Tissues via NeRF", Mar 2023.
Invited speaker at TUM: "CAMP Learning Day: NeRF meets Medical Imaging", Oct 2022.

Teaching

Multimedia Coding and Processing (Fall 2023) @ CUHK (TA)
Fundamentals of Artificial Intelligence (Fall 2021, Fall 2022) @ CUHK (TA)
Computer Graphics (Spring 2021) @ ShanghaiTech (TA)
Linear Algebra (Fall 2019, Fall 2020) @ ShanghaiTech (TA)
Introduction to Computer Programming (Fall 2018) @ ShanghaiTech (TA)

Miscellaneous

Outside of academics, my hobbies include playing the guitar, creative coding, web design, and developing video games. Check out my showcase!